Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3334 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.9305. Min Range: -0.9305

Max Act: 0.8811. Min Act: -0.0000

Data Index: 145990 (C4 (Web Text))

Max Activating Token Index: 719

Text #1

Max Range: 0.9305. Min Range: -0.9305

Max Act: 0.9305. Min Act: -0.0000

Data Index: 734846 (C4 (Web Text))

Max Activating Token Index: 59

Text #2

Max Range: 0.9305. Min Range: -0.9305

Max Act: 0.9104. Min Act: -0.0000

Data Index: 513004 (C4 (Web Text))

Max Activating Token Index: 965

Text #3

Max Range: 0.9305. Min Range: -0.9305

Max Act: 0.6863. Min Act: -0.0000

Data Index: 1510682 (Python Code)

Max Activating Token Index: 673

Text #4

Max Range: 0.9305. Min Range: -0.9305

Max Act: 0.7901. Min Act: -0.0000

Data Index: 1653199 (Python Code)

Max Activating Token Index: 198

Text #5

Max Range: 0.9305. Min Range: -0.9305

Max Act: 0.8318. Min Act: -0.0000

Data Index: 1581406 (Python Code)

Max Activating Token Index: 844

Text #6

Max Range: 0.9305. Min Range: -0.9305

Max Act: 0.7950. Min Act: -0.0000

Data Index: 1594562 (Python Code)

Max Activating Token Index: 187

Text #7

Max Range: 0.9305. Min Range: -0.9305

Max Act: 0.8018. Min Act: -0.0000

Data Index: 1563348 (Python Code)

Max Activating Token Index: 977

Text #8

Max Range: 0.9305. Min Range: -0.9305

Max Act: 0.7490. Min Act: -0.0000

Data Index: 198889 (C4 (Web Text))

Max Activating Token Index: 904

Text #9

Max Range: 0.9305. Min Range: -0.9305

Max Act: 0.7422. Min Act: -0.0000

Data Index: 1198246 (C4 (Web Text))

Max Activating Token Index: 164

Text #10

Max Range: 0.9305. Min Range: -0.9305

Max Act: 0.7894. Min Act: -0.0000

Data Index: 1458669 (Python Code)

Max Activating Token Index: 669

Text #11

Max Range: 0.9305. Min Range: -0.9305

Max Act: 0.7205. Min Act: -0.0000

Data Index: 505655 (C4 (Web Text))

Max Activating Token Index: 711

Text #12

Max Range: 0.9305. Min Range: -0.9305

Max Act: 0.7419. Min Act: -0.0000

Data Index: 904173 (C4 (Web Text))

Max Activating Token Index: 529

Text #13

Max Range: 0.9305. Min Range: -0.9305

Max Act: 0.7182. Min Act: -0.0000

Data Index: 284842 (C4 (Web Text))

Max Activating Token Index: 78

Text #14

Max Range: 0.9305. Min Range: -0.9305

Max Act: 0.7073. Min Act: -0.0000

Data Index: 1323278 (C4 (Web Text))

Max Activating Token Index: 986

Text #15

Max Range: 0.9305. Min Range: -0.9305

Max Act: 0.8261. Min Act: -0.0000

Data Index: 1187805 (C4 (Web Text))

Max Activating Token Index: 78

Text #16

Max Range: 0.9305. Min Range: -0.9305

Max Act: 0.7021. Min Act: -0.0000

Data Index: 1488444 (Python Code)

Max Activating Token Index: 356

Text #17

Max Range: 0.9305. Min Range: -0.9305

Max Act: 0.7794. Min Act: -0.0000

Data Index: 886927 (C4 (Web Text))

Max Activating Token Index: 235

Text #18

Max Range: 0.9305. Min Range: -0.9305

Max Act: 0.7461. Min Act: -0.0000

Data Index: 1386265 (Python Code)

Max Activating Token Index: 191

Text #19

Max Range: 0.9305. Min Range: -0.9305

Max Act: 0.7463. Min Act: -0.0000

Data Index: 1290894 (C4 (Web Text))

Max Activating Token Index: 109